Publication

Probabilistic Adaptive Control for Robust Behavior Imitation

Abstract

In the context of learning from demonstration (LfD), trajectory policy representations such as probabilistic movement primitives (ProMPs) allow for rich modeling of demonstrated skills. To reproduce a learned skill with a real robot, a feedback controller is required to cope with perturbations and to react to dynamic changes in the environment. In this paper, we propose a generalized probabilistic control approach that merges the probabilistic modeling of the demonstrated movements and the feedback control action for reproducing the demonstrated behavior. We show that our controller can be easily employed, outperforming both original controller and a controller with constant feedback gains. Furthermore, we show that the proposed approach is able to solve dynamically changing tasks by modeling the demonstrated behavior as Gaussian mixtures and by introducing context variables. We demonstrate the capability of the approach with experiments in simulation and by teaching a 7-axis Franka Emika Panda robot to drop a ball into a moving box with only few demonstrations.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Related concepts (32)
Feedback
Feedback occurs when outputs of a system are routed back as inputs as part of a chain of cause-and-effect that forms a circuit or loop. The system can then be said to feed back into itself. The notion of cause-and-effect has to be handled carefully when applied to feedback systems: Simple causal reasoning about a feedback system is difficult because the first system influences the second and second system influences the first, leading to a circular argument.
Negative feedback
Negative feedback (or balancing feedback) occurs when some function of the output of a system, process, or mechanism is fed back in a manner that tends to reduce the fluctuations in the output, whether caused by changes in the input or by other disturbances. Whereas positive feedback tends to lead to instability via exponential growth, oscillation or chaotic behavior, negative feedback generally promotes stability. Negative feedback tends to promote a settling to equilibrium, and reduces the effects of perturbations.
Closed-loop controller
A closed-loop controller or feedback controller is a control loop which incorporates feedback, in contrast to an open-loop controller or non-feedback controller. A closed-loop controller uses feedback to control states or outputs of a dynamical system. Its name comes from the information path in the system: process inputs (e.g., voltage applied to an electric motor) have an effect on the process outputs (e.g., speed or torque of the motor), which is measured with sensors and processed by the controller; the result (the control signal) is "fed back" as input to the process, closing the loop.
Show more
Related publications (48)

A geometric optimal control approach for imitation and generalization of manipulation skills

Sylvain Calinon, Amirreza Razmjoo Fard, Jie Zhao

Daily manipulation tasks are characterized by regular features associated with the task structure, which can be described by multiple geometric primitives related to actions and object shapes. Only using Cartesian coordinate systems cannot fully represent ...
ELSEVIER2023

Closed-loop technique based on gain balancing for real-time Brillouin optical time-domain analysis

Luc Thévenaz, Zhisheng Yang, Li Zhang, Ana Gabriela Correa Mena

A closed-loop servo control based on balancing the gain of two probing frequencies is proposed for real-time Brillouin optical time-domain analysis (BOTDA) without post-processing. With the most basic BOTDA hardware setup, the system can perform measuremen ...
2022

Breaking Silos to Guarantee Control Stability with Communication over Ethernet TSN

Amir Aminifar

Editor's notes: The cross-layer approach presented in this article involves co-designing a feedback controller's parameters together with the schedule of an Ethernet network used for communicating state information and control signals.-Samarjit Chakraborty ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021
Show more
Related MOOCs (13)
Thymio: un robot pour se former à l'informatique
On propose dans ce MOOC de se former à et avec Thymio : apprendre à programmer le robot Thymio et ce faisant, s’initier à l'informatique et la robotique.
The Thymio robot as a tool for discovering digital science
This MOOC teaches basic understanding of robots’ mechanisms and Thymio’s programming languages, classroom use and pedagogical elements.
The Thymio robot as a tool for discovering digital science
This MOOC teaches basic understanding of robots’ mechanisms and Thymio’s programming languages, classroom use and pedagogical elements.
Show more

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.